Agent infrastructure

Agent infrastructure is the runtime layer that agents need beyond a model and a framework: isolated sandboxes for executing generated code, cloud browsers for acting on websites, memory services for recalling past interactions, and durable execution engines that keep long-running tasks alive through failures.

Code sandboxes such as E2B, Daytona, Modal Sandboxes, and Vercel Sandbox start isolated machines on demand, while microsandbox and the Kubernetes Agent Sandbox project run on infrastructure you control. Browser providers such as Browserbase, Steel, and Browser Use host headless browsers for agents. Memory layers such as Mem0, Zep, and Cognee extract facts from conversations and retrieve them in later sessions.

Durable execution engines, including Temporal, Inngest, Restate, and DBOS, persist each step of a workflow so an agent loop can pause, retry, and resume. The large clouds bundle several of these pieces into managed agent runtimes: Amazon Bedrock AgentCore, Microsoft Foundry Agent Service, and Google Cloud's Agent Runtime.

Agent infrastructure compared

PlatformOpen sourceDeploymentBest for
Agent Runtime (Gemini Enterprise Agent Platform)NoManaged cloudDeploying ADK or LangGraph agents on Google Cloud
Agent Sandbox (Kubernetes)Yes (Apache-2.0)Self-hostedPlatform teams running agent sandboxes on Kubernetes
Amazon Bedrock AgentCoreNoManaged cloudRunning framework-agnostic agents on AWS
Anchor BrowserNoManaged cloudEnterprise automation of web-based operations
BlaxelNoManaged cloudAgents that pause and resume sandboxes often
Browser UseYes (MIT)Library, CLI, Managed cloudLLM-driven web agents in Python
BrowserbaseNoManaged cloudCloud browsers for agents that need the live web
BrowserlessNoManaged cloud, Self-hostedPuppeteer and Playwright workloads at scale
Cloudflare SandboxesNoManaged cloudAgents built on Cloudflare Workers
CogneeYes (Apache-2.0)Library, Self-hosted, Managed cloudGraph-based agent memory you can self-host
DaytonaNoManaged cloudStateful sandboxes for coding and agent workloads
DBOSYes (MIT)LibraryDurable agents on an existing Postgres database
E2BYes (Apache-2.0)Managed cloud, Self-hostedRunning agent-generated code in isolated machines
HatchetYes (MIT)Managed cloud, Self-hostedTask queues and durable agent workflows together
HyperbrowserNoManaged cloudBrowser sessions and sandboxes from one provider
InngestNoManaged cloud, Self-hostedEvent-driven agent steps in serverless apps
KernelNoManaged cloudAgents that need logged-in, reusable browser sessions
LangMemYes (MIT)LibraryLangGraph agents that need long-term memory
LightpandaYes (AGPL-3.0)Self-hosted, LocalLightweight headless browsing at high concurrency
Mem0Yes (Apache-2.0)Library, Self-hosted, Managed cloudPersonalized agents that remember users across sessions
microsandboxYes (Apache-2.0)Local, Self-hostedLocal, hardware-isolated sandboxes for agents
Microsoft Foundry Agent ServiceNoManaged cloudEnterprise agents on Azure with Entra identity
Modal SandboxesNoManaged cloudHigh-volume agent and reinforcement learning workloads
Northflank SandboxesNoManaged cloudTeams already deploying workloads on Northflank
RestateNoSelf-hostedDurable agent logic with low-latency state
SteelYes (Apache-2.0)Managed cloud, Self-hostedSelf-hostable browser sessions for agents
SupermemoryNoManaged cloud, APIAdding user memory to agents through an API
TemporalYes (MIT)Self-hosted, Managed cloudLong-running agents that must survive failures
Trigger.devYes (Apache-2.0)Managed cloud, Self-hostedTypeScript teams running long background agent tasks
Vercel SandboxNoManaged cloudApps on Vercel that execute generated code
Workflow SDKYes (Apache-2.0)LibraryDurable agent steps in TypeScript web frameworks
ZepNoManaged cloudAgents that need memory of facts that change over time

Profiles

  • Agent Runtime (Gemini Enterprise Agent Platform) logo

    Agent Runtime (Gemini Enterprise Agent Platform)

    Google Cloud · docs.cloud.google.com

    Agent Runtime is the managed agent hosting service in Google Cloud's Gemini Enterprise Agent Platform, deploying ADK, LangGraph, LangChain, AG2, and custom agents with sessions, Memory Bank, sandboxed code execution, and evaluation services.

    • Managed cloud
  • Agent Sandbox (Kubernetes) logo

    Agent Sandbox (Kubernetes)

    Kubernetes SIG Apps · agent-sandbox.sigs.k8s.io

    Agent Sandbox is a Kubernetes SIG Apps project that adds a Sandbox custom resource and controller for isolated, stateful, singleton workloads such as agent runtimes, delegating isolation to runtimes like gVisor or Kata Containers.

    • Open source · Apache-2.0
    • Self-hosted
  • Amazon Bedrock AgentCore logo

    Amazon Bedrock AgentCore

    Amazon Web Services · aws.amazon.com

    Amazon Bedrock AgentCore is a set of AWS services for running agents built with any framework and model, including a serverless runtime with session isolation, a managed agent runtime, memory, gateway, identity, browser, code interpreter, and observability.

    • Managed cloud
  • Anchor Browser logo

    Anchor Browser

    anchorbrowser.io

    Anchor provides secure browser infrastructure for computer-use AI agents, letting teams deploy fleets of cloud browser agents that automate web tasks otherwise done by people in enterprise operations.

    • Managed cloud
  • Blaxel logo

    Blaxel

    blaxel.ai

    Blaxel is infrastructure for autonomous agents built on microVM sandboxes that boot and resume in milliseconds, with shared memory and programmable networking for agents that run code and tools between long idle periods.

    • Managed cloud
  • Browser Use logo

    Browser Use

    browser-use.com

    Browser Use is an open-source Python library for browser agents that operate websites with any LLM, plus a cloud service that provides hosted web agents and stealth browsers that other agent frameworks can connect to.

    • Open source · MIT
    • Library
    • CLI
    • Managed cloud
    • Python
  • Browserbase logo

    Browserbase

    browserbase.com

    Browserbase runs headless browsers in the cloud for AI agents and automations, and it maintains Stagehand, an MIT-licensed framework for browser automations that combine code with natural-language instructions.

    • Managed cloud
  • Browserless

    browserless.io

    Browserless runs cloud browsers for AI agents and automation that connect over MCP, Puppeteer, or Playwright, with stealth and authenticated profiles; its self-hostable code is source-available under SSPL-1.0 or a commercial license.

    • Managed cloud
    • Self-hosted
  • Cloudflare Sandboxes logo

    Cloudflare Sandboxes

    Cloudflare · developers.cloudflare.com

    Cloudflare Sandboxes execute untrusted or generated code in Linux virtual machines or isolated Workers, managed from Workers through Cloudflare's open-source Sandbox SDK, for agents that already run on Cloudflare's developer platform.

    • Managed cloud
    • TypeScript
  • Cognee logo

    Cognee

    cognee.ai

    Cognee is an open-source memory platform for LLM agents that builds persistent memory across sessions with graph, vector, and relational retrieval, running self-hosted, in Docker, on-premises, or on Cognee Cloud.

    • Open source · Apache-2.0
    • Library
    • Self-hosted
    • Managed cloud
    • Python
  • Daytona

    daytona.io

    Daytona runs secure, elastic sandboxes for AI-generated code with stateful operations and SDKs for agents; in June 2026 Daytona moved core development to a private codebase and stopped updating its formerly open-source GitHub repository.

    • Managed cloud
  • DBOS logo

    DBOS

    dbos.dev

    DBOS is an open-source durable workflow library built on Postgres: developers annotate workflows and steps in their code to make them durable, with no separate orchestrator to operate, for agent loops, queues, and scheduled jobs.

    • Open source · MIT
    • Library
    • Python
    • TypeScript
    • Go
  • E2B logo

    E2B

    e2b.dev

    E2B provides isolated sandboxes in which AI agents run code, browse, and use tools, with pause and fork support; its SDKs and infrastructure are open source, and sandboxes run in E2B's cloud or a customer's AWS, GCP, or Azure account.

    • Open source · Apache-2.0
    • Managed cloud
    • Self-hosted
    • Python
    • TypeScript
  • Hatchet logo

    Hatchet

    hatchet.run

    Hatchet is an open-source orchestration engine for background tasks, AI agents, and durable workflows, with SDKs for Python, TypeScript, Go, and Ruby, available as Hatchet Cloud or self-hosted.

    • Open source · MIT
    • Managed cloud
    • Self-hosted
    • Python
    • TypeScript
    • Go
  • Hyperbrowser logo

    Hyperbrowser

    hyperbrowser.ai

    Hyperbrowser provides cloud browsers, isolated sandboxes, and web data APIs for AI agents, starting Chrome sessions and microVMs through one API that Playwright, Puppeteer, or agent frameworks connect to; its HyperAgent library is AGPL-licensed.

    • Managed cloud
  • Inngest

    inngest.com

    Inngest is a durable execution platform for background jobs, workflows, and AI agents, where step functions written with its SDKs get retries, flow control, and step-level observability; its server is source-available under SSPL with a delayed Apache-2.0 license.

    • Managed cloud
    • Self-hosted
    • TypeScript
    • Python
    • Go
  • Kernel logo

    Kernel

    kernel.sh

    Kernel is browser infrastructure for AI agents and web automations, with autoscaling cloud browsers, reusable sessions, and managed authentication, and it publishes its browser container images as open source under Apache-2.0.

    • Managed cloud
  • LangMem logo

    LangMem

    LangChain · langchain-ai.github.io

    LangMem is LangChain's open-source Python library for agent long-term memory, with tools agents call to record and search memories, a background manager that extracts and consolidates knowledge, prompt refinement, and native LangGraph store integration.

    • Open source · MIT
    • Library
    • Python
  • Lightpanda logo

    Lightpanda

    lightpanda.io

    Lightpanda is an open-source headless browser written from scratch in Zig for machines rather than people, designed for web automation and AI agents with a smaller memory footprint than headless Chrome.

    • Open source · AGPL-3.0
    • Self-hosted
    • Local
    • Zig
  • Mem0 logo

    Mem0

    mem0.ai

    Mem0 is a memory layer for AI agents and applications that extracts, stores, and retrieves facts from past interactions so agents can personalize responses, available as an Apache-2.0 open-source library and a managed platform.

    • Open source · Apache-2.0
    • Library
    • Self-hosted
    • Managed cloud
    • Python
    • TypeScript
  • microsandbox logo

    microsandbox

    microsandbox.dev

    microsandbox is an open-source microVM sandbox for AI agents and untrusted code that runs locally on macOS, Linux, and Windows or on self-hosted servers, with access to a managed cloud version available on request.

    • Open source · Apache-2.0
    • Local
    • Self-hosted
  • Microsoft Foundry Agent Service logo

    Microsoft Foundry Agent Service

    Microsoft · learn.microsoft.com

    Microsoft Foundry Agent Service hosts prompt agents, voice agents, and containerized hosted agents built with Agent Framework, LangGraph, or other SDKs, with toolboxes exposed over MCP, Microsoft Entra agent identities, tracing, and A2A endpoints.

    • Managed cloud
  • Northflank Sandboxes logo

    Northflank Sandboxes

    Northflank · northflank.com

    Northflank Sandboxes are isolated microVM environments for running untrusted and AI-generated code at scale, offered as part of Northflank's cloud platform for deploying and operating application workloads.

    • Managed cloud
  • Restate logo

    Restate

    restate.dev

    Restate is a durable runtime for agents and backends that packs durable execution, keyed state, queues, RPC, timers, and flow control into a single binary; the server is source-available under the Business Source License 1.1.

    • Self-hosted
    • TypeScript
    • Java
    • Python
  • Steel logo

    Steel

    steel.dev

    Steel is an open-source browser API for AI agents that manages sessions, pages, and Chrome processes, with control through Puppeteer, Playwright, or Selenium over CDP, available as a self-hosted server or a managed cloud service.

    • Open source · Apache-2.0
    • Managed cloud
    • Self-hosted
  • Supermemory

    supermemory.ai

    Supermemory is a memory and context engine for AI agents that extracts facts from conversations, maintains user profiles, handles contradictions and expiring information, and adds retrieval and connectors, offered through an API, plugins, and MCP.

    • Managed cloud
    • API
  • Temporal

    Temporal Technologies · temporal.io

    Temporal is an open-source durable execution platform whose server runs workflows that survive process crashes and outages by persisting each step and retrying failures, available self-hosted or as Temporal Cloud and used for long-running agent loops.

    • Open source · MIT
    • Self-hosted
    • Managed cloud
    • Go
    • Java
    • Python
  • Trigger.dev logo

    Trigger.dev

    trigger.dev

    Trigger.dev is an open-source platform for durable AI agents and workflows in TypeScript that runs long-running tasks with retries, queues, and LLM observability, available as a managed cloud or self-hosted.

    • Open source · Apache-2.0
    • Managed cloud
    • Self-hosted
    • TypeScript
  • Vercel Sandbox logo

    Vercel Sandbox

    Vercel · vercel.com

    Vercel Sandbox runs AI-generated, customer, or other untrusted code in isolated, ephemeral virtual machines on Vercel's infrastructure, controlled through an Apache-2.0 SDK from Vercel functions or other environments.

    • Managed cloud
    • TypeScript
  • Workflow SDK logo

    Workflow SDK

    Vercel · workflow-sdk.dev

    Workflow SDK is Vercel's open-source TypeScript library that makes async functions durable through a use workflow directive, so apps and agents can suspend, resume, and keep state, with deployment on Vercel, other clouds, or Docker.

    • Open source · Apache-2.0
    • Library
    • TypeScript
  • Zep logo

    Zep

    getzep.com

    Zep is a context layer for agents that builds a temporal knowledge graph from conversations and business data using its open-source Graphiti library; Zep's self-hosted Community Edition is deprecated, so Zep itself is offered as Zep Cloud.

    • Managed cloud

How to choose

01Isolation model
MicroVMs, hardened container runtimes such as gVisor or Kata Containers, and plain containers give different security boundaries for untrusted, model-generated code.
02Session lifecycle
Start time, maximum session length, and pause, resume, snapshot, or fork support determine whether an agent can keep state between steps.
03Deployment and data location
Managed services are quickest to adopt, while self-hosted or bring-your-own-cloud options keep code, browser sessions, and memories inside your own network.
04Licensing
Some entries are open source, while others are source-available under licenses such as SSPL or the Business Source License that restrict offering the software as a competing service.
05SDKs and integrations
Official SDK languages and ready-made integrations with agent frameworks, Playwright or Puppeteer, and MCP reduce glue code.
06Observability and controls
Session recordings, step-level traces, audit logs, and network egress controls help teams debug agents and enforce security policy.

Frequently asked questions

What is an AI agent sandbox?

An AI agent sandbox is an isolated computing environment, usually a microVM or hardened container, where an agent can run code, install packages, and edit files without access to the host system or other tenants. Sandboxes are created on demand through an API, can often be paused or snapshotted, and are destroyed when the task ends. E2B, Daytona, and Modal Sandboxes are examples.

What is agent memory in AI?

Agent memory is the set of mechanisms that let an AI agent keep information beyond a single context window, such as user preferences, facts learned in earlier sessions, and summaries of past tasks. Memory layers extract these items from conversations, store them in vector, graph, or relational databases, and retrieve the relevant ones into later prompts. Mem0, Zep, Cognee, and LangMem are examples.

What is durable execution?

Durable execution is a programming model in which an engine records the result of each workflow step, so a program that crashes, times out, or waits days for human approval resumes from the last completed step instead of starting over. Agents use it for long-running loops with many model and tool calls. Temporal, Inngest, Restate, DBOS, and Trigger.dev provide durable execution.

E2B vs Daytona: what is the difference?

Both services start isolated sandboxes for AI-generated code through SDKs. E2B publishes its SDKs and sandbox infrastructure under Apache-2.0 and can run sandboxes in E2B's cloud or in a customer's AWS, GCP, or Azure account. Daytona offers managed, stateful sandboxes; in June 2026 it moved core development to a private codebase and stopped updating its formerly open-source repository.

Related guides

AI agents hub

Other categories

Product details change quickly; check each vendor’s site for current features, licensing and pricing.